OpensourceThai/Wilai

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 1
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.56.0
+- Transformers 4.56.1
 - Pytorch 2.8.0+cu126
 - Datasets 4.0.0
 - Tokenizers 0.22.0

config.json

@@ -17,7 +17,7 @@
   "pad_token_id": 0,
   "rope": true,
   "top_k": 2,
-  "transformers_version": "4.56.0",
+  "transformers_version": "4.56.1",
   "use_flashattn": true,
   "vocab_size": 48000
 }

generation_config.json

@@ -8,5 +8,5 @@
   "pad_token_id": 0,
   "temperature": 0.7,
   "top_p": 0.9,
-  "transformers_version": "4.56.0"
+  "transformers_version": "4.56.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd22b05bf1e5c4195a7b93b522c53c2469df16f1fc0cbe40258ec5d53b832f19
+oid sha256:5e1b15b691eb1a8abe0cf263fb2c66702cb3dc4476cfa945152e8abc3646db74
 size 664188751

runs/Sep08_03-09-32_e7c9d734d21f/events.out.tfevents.1757300975.e7c9d734d21f.597.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f449bd9967575caa81f4d885b20a0988dd96d88e5c96ee766eea3c17d845f97b
+size 38223

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec69372609b6c8a301c0d74a994c48118e070574b499d9dce75820ea560c0e9c
+oid sha256:260edcef99f5c590cea91a68c06afb3fbf2b22114a949275810607d6481f8261
 size 5777